Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Indian and Amharic scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙜
    0.95
    িনবার্গ
    0.94
    𝙪
    0.92
    𝓀
    0.92
    𝙨
    0.89
    ्लादेश
    0.89
    Ⲕ
    0.89
    𝙡
    0.89
    лянчук
    0.89
    خستان
    0.89
    POSITIVE LOGITS
    0.69
    <0xE0>
    0.65
    க்
    0.59
    ‍
    0.57
     வி
    0.55
     ગ
    0.54
     /
    0.54
    ‌
    0.54
     '
    0.51
     -
    0.50
    Act Density 0.006%

    No Known Activations